Factor enhanced DeepSurv: A deep learning approach for predicting survival probabilities in cirrhosis data

• Published in: Computers in biology and medicine Vol. 189; p. 109963
• Main Authors: Obite, Chukwudi Paul, Chukwudi, Emmanuella Onyinyechi, Uchechukwu, Merit, Nwosu, Ugochinyere Ihuoma
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.05.2025
• Subjects: Cirrhosis; Cox model; Deep Learning; Deep neural network; Factor enhanced DeepSurv; Female; Humans; Internal Medicine; Liver Cirrhosis - mortality; Male; Middle Aged; Other; Proportional Hazards Models; Random survival forest; Survival Analysis; Cirrhosis; Deep neural network; Random survival forest; Cox model; Factor enhanced DeepSurv
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2025.109963

Over the years, various models, including both traditional and machine learning models, have been employed to predict survival probabilities for diverse survival datasets. The objective is to obtain models that provide more accurate estimates of survival probabilities. Certain datasets exhibit complex nonlinear effects and interactions between variables that may necessitate the application of deep learning algorithms to comprehend the underlying data generation process. In this paper, we introduced Factor Enhanced DeepSurv (FE-DeepSurv), a novel deep neural network designed to study complex structures and excels at filtering noise within predictors, thereby enhancing precision of survival probability estimates. FE-DeepSurv incorporates factor analysis to reduce predictor dimensionality, applies a transformation technique to account for data censoring, and employs a deep neural network to predict conditional failure probabilities for each time interval. These predictions are subsequently utilized to estimate survival probabilities for each subject. We applied our proposed model to study cirrhosis survival data, a secondary data from Mayo Clinic trial focused on primary biliary cirrhosis (PBC) of the liver and compared its performance with the Cox proportional hazard model (Cox model), random survival forest (RSF), DeepHit, and DeepSurv, using the concordance index (C-index), brier score (BS), and integrated brier score (IBS). The results show that FE-DeepSurv outperforms many existing survival models. FE-DeepSurv's accurate predictions of survival probabilities and hazard rates can drive improvements in clinical practice, healthcare management, insurance risk assessment, and various other domains. By adopting FE-DeepSurv, institutions can harness the power of advanced analytics to make more informed decisions, ultimately leading to better outcomes across multiple sectors. •We proposed FE-DeepSurv, a deep neural network for estimating survival probabilities with improved accuracy.•We applied FE-DeepSurv to cirrhosis data and compared its performance with Cox, RSF, DeepHit and DeepSurv.•FE-DeepSurv outperformed RSF, Cox, DeepHit and DeepSurv in modeling cirrhosis survival probabilities.•FE-DeepSurv enhances clinical decisions, resource allocation, and treatment planning, improving patient outcomes.